Play 73
Waste & Recycling Optimizer
Medium✅ Ready
AI-powered waste management — material classification, route optimization, contamination detection.
AI-powered waste management system combining computer vision material classification, collection route optimization, and contamination detection. Azure AI Vision identifies waste types (recyclable/compostable/landfill) from camera feeds, OpenAI generates route optimization considering vehicle capacity and pickup schedules, IoT Hub tracks bin fill levels, and Cosmos DB stores recycling rate analytics for municipality dashboards.
Architecture Pattern
Vision + IoT waste management: material classification → route optimization → contamination alerts
Azure Services
Azure AI VisionAzure OpenAIAzure IoT HubContainer AppsCosmos DB
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Waste Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (186 lines), evaluate (132 lines), tune (230 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with Custom Vision + Maps inputs + envFile
TuneKit (AI Config)
- config/openai.json — classification and optimization prompts
- config/waste.json — material categories, vehicle capacity, pickup windows
- config/guardrails.json — classification confidence thresholds
- evaluation/eval.py — Classification accuracy >90%, Route efficiency >85%
Tuning Parameters
Material categoriesClassification confidence thresholdVehicle capacity constraintsPickup time windowsContamination sensitivity
Estimated Cost
Dev/Test
$60–150/mo
Production
$1.5K–5K/mo